基于改进型相关向量机的高光谱图像分类

相关向量机(RVM)高光谱图像分类算法是一种基于贝叶斯概率模型的监督机器学习算法,其分类精度较高、测试时间较短。然而算法本身存在训练时间随着训练样本增加直线上升、分类效率整体降低等问题。针对这种情况,提出一种基于改进型相关向量机(VRVM)的高光谱图像分类算法。本算法在传统概率模型中引入一个新的分布,使得计算复杂度较高的积分运算可近似地拆分成两个较为简单的对数和形式。实验结果表明,VRVM高光谱图像分类算法的总体分类精度和相关向量的数量与RVM基本相同,但训练时间随样本数的增加有明显的减少。     

Enhanced Optical Image Verification Based on Joint Transform Correlator Adopting Fourier Hologram

In this paper two new architectures for optical image verification are proposed. Both architectures are based on conventional joint transform correlators (JTCs) adopting a Fourier hologram and can significantly improve the recovered image quality. First, an input phase-only function is Fourier transformed and then interferes with a reference wave that is diffracted from a plane wave incident on another random phase mask. Second, two phase-only functions are placed at the two input sides of a beamsplitter such that the interference pattern of their Fourier transforms can be detected. To obtain a predefined target image in the output plane, one of the input phase functions is iteratively retrieved by the use of the projection onto constraint sets algorithm. Simulation results show that the less mean squared error and better image quality are obtained for both the binary and grayscale images.     

Optimal control of coupled spin dynamics: design of NMR pulse sequences by gradient ascent algorithms

In this paper, we introduce optimal control algorithm for the design of pulse sequences in NMR spectroscopy. This methodology is used for designing pulse sequences that maximize the coherence transfer between coupled spins in a given specified time, minimize the relaxation effects in a given coherence transfer step or minimize the time required to produce a given unitary propagator, as desired. The application of these pulse engineering methods to design pulse sequences that are robust to experimentally important parameter variations, such as chemical shift dispersion or radiofrequency (rf) variations due to imperfections such as rf inhomogeneity is also explained.     

Efficient inverse radiation analysis in a cylindrical geometry using a combined method of hybrid genetic algorithm and finite-difference Newton method

An inverse radiation problem was considered to estimate boundary conditions such as temperature distribution and emissivity in axisymmetric absorbing, emitting, and scattering medium, given the measured incident radiative heat fluxes. The finite-volume method was employed to solve a direct radiative transfer equation for a two-dimensional axisymmetric geometry. Various parameter estimators, such as conjugate-gradient method, hybrid genetic algorithm, and finite-difference Newton method, were employed to solve the inverse problems, while discussing their performances in terms of estimation accuracy and computational efficiency. Based on this, we proposed, as a best inverse analysis tool, a new combined method that adopted the hybrid genetic algorithm as an initial value selector and used the finite-difference Newton method as a parameter estimator.     

高精度动态光纤应变传感研究

传统的光纤应变传感技术无法在满足高精度和强环境适应性的同时实现稳定的动态应变传感.为了解决该问题,本文将光干涉原理应用于光纤应变传感,设计了一种强环境适应性的基于干涉结构的高精度光纤应变传感系统,基于扫频干涉信号的互相关系数,该系统可以稳定地探测应变.本文还提出一种动态探测算法,该算法弥补了系统只能探测较小应变的缺陷,大大提升了实际应变的探测范围,同时还实现了动态的应变检测;采用三次样条插值算法,提升了小应变探测的精度.理论分析和仿真模拟表明,在加入白噪声的信号信噪比为15dB时,插值后的探测精度是未插值探测精度的2.3倍,插值后本系统探测结果的最大误差只有约9nε.     

改进人工蜂群算法优化ELM分类模型

针对极限学习机(Extreme Learning Machine,ELM)参数优化问题,提出改进人工蜂群算法(Improvement Artificial bee colony, IABC)优化ELM分类模型。算法采用解更新策略池代替固定不变的更新策略,将邻域搜索自适应化;优化侦察蜂搜索方式,利用Kent映射产生均匀性更优的初始随机数序列。在分类数据集中,将IABC-ELM分类模型同ELM、PSO-ELM分类模型进行对比实验。实验中,IABC-ELM模型取得了最佳的分类结果,得到了最低的输出权重范数。结果表明,IABC-ELM模型分类效果显著优于对比模型,证实了IABC算法优化ELM分类模型的有效性和优越性。     

低照度条件下超分辨率人脸图像采集系统设计与实现

在计算机技术高速发展的时代,多平台计算机视觉库随之产生。OpenCV作为一种开源代码的计算机视觉库,以可兼容多平台、接口广泛的特点被广泛运用各个领域。在低照度条件下,会出现光照环境差异过大或光线不足等情况,导致传统图像采集系统不能采集高质量的人脸图像,局限性较差。提出基于OpenCV在C 环境配置下运用三维人脸识别技术算法,设计一套低照度条件下超分辨率人脸图像采集系统。实验证明,该设计方案具有实时(对焦速度快)、快速(单张采集0.05秒)、准确(面部识别率99.3%)等特点,能够充分满足低照度条件下超分辨率人脸图像采集的需求。     

基于改进蚁群算法的LEACH协议研究

针对LEACH协议在数据传输阶段,簇首与汇聚节点之间采用单跳模式传输数据使得能量消耗快并且不均衡的问题,提出一种基于改进蚁群算法的新型路由协议。该协议利用了能耗因子对蚁群转移概率以及信息素更新进行改进,充分考虑了节点的剩余能量和节点间距离,通过信息素的建立和更新,寻找簇首节点和基站之间的最优传输路径,进行多跳传输模式,从而均衡簇首节点能量消耗。仿真实验结果表明,改进后的ACO-BEC协议较之于LEACH协议,能够有效降低了整个网络能量消耗,延长了网络寿命。     

基于非均匀分簇的无线传感器网络路由协议

在无线传感器网络中,分簇技术是一种有效延长网络生命周期的方法。但是这种多跳的网络模型,如果节点均匀分布并且簇的大小相等,则靠近基站的簇头由于要中继更多的数据,则会导致能量空洞现象。因此提出一种非均匀分簇方法来缓解能量空洞问题。首先,通过节点的剩余能量、到基站的距离以及邻居节点数量来选择簇头。簇一旦形成之后,通过单跳和多跳的混合机制将数据发送到基站。实验结果表明,此协议能有效的延长网络的生命周期,均衡网络能耗,有效延缓能量空洞的形成速度。     

K-SVD和OMP算法在超声信号去噪中的应用

针对在线采集时超声波检测信号中存在大量噪声,降低了材料内部缺陷诊断准确性的问题,提出了一种基于广义K+奇异值分解算法(K-SVD)和正交匹配追踪算法(OMP)相结合的超声回波信号去噪算法。该算法利用K-SVD算法将Gabor字典训练成能够最有效反映信号结构特征的超完备字典,然后基于训练完成的超完备字典,用OMP算法把一定数量的字典原子进行线性组合来构成原始信号,从而实现信号的去噪。通过仿真实验将本文方法与传统的小波阈值去噪方法进行了对比研究。实验结果表明,该方法对超声回波信号的去噪效果优于小波阈值去噪方法,且噪声越大对比越明显,不仅可更有效地滤除信号中的高斯白噪声,提高信噪比,且尽可能保留了原始信号有用信息。